Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1196 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.8286. Min Act: -0.0000

Data Index: 1551722 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7200. Min Act: -0.0000

Data Index: 1428059 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1520935 (The Pile)

Max Activating Token Index: 337

Text #3

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6988. Min Act: -0.0000

Data Index: 1026689 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1484632 (The Pile)

Max Activating Token Index: 591

Text #5

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6163. Min Act: -0.0000

Data Index: 986816 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1116325 (The Pile)

Max Activating Token Index: 535

Text #7

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.5994. Min Act: -0.0000

Data Index: 86738 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6367. Min Act: -0.0000

Data Index: 116442 (The Pile)

Max Activating Token Index: 404

Text #9

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6617. Min Act: -0.0000

Data Index: 1544908 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6002. Min Act: -0.0000

Data Index: 474670 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6130. Min Act: -0.0001

Data Index: 605243 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1305469 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6098. Min Act: -0.0000

Data Index: 612642 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6097. Min Act: -0.0000

Data Index: 986340 (The Pile)

Max Activating Token Index: 672

Text #15

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1563489 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1634190 (The Pile)

Max Activating Token Index: 926

Text #17

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1532440 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.5952. Min Act: -0.0000

Data Index: 959862 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 0.8286. Min Range: -0.8286

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1733478 (The Pile)

Max Activating Token Index: 82